Edge ML

ML: Machine Learning

Edge machine learning studies how to run useful prediction and learning directly on devices such as sensors, phones, microcontrollers, and embedded accelerators. Common approaches include quantization, pruning, distillation, and hardware-aware architecture search, alongside federated learning and cloud-edge collaboration when devices need to share updates or offload computation. Applications range from health and agriculture to industrial monitoring, with growing work on continual learning and on-device fine-tuning as conditions change. The central challenge is balancing accuracy, energy, memory, latency, privacy, and robustness, while evaluating systems on their actual hardware and under realistic data and network shifts.

Latest papers

130 papers12 papers in the last four weeks, up 20% on the four weeks before. 0.1% of all new papers.

Mar 10, 2026

TrainDeeploy: Hardware-Accelerated Parameter-Efficient Fine-Tuning of Small Transformer Models at the Extreme Edge

On-device tuning of deep neural networks enables long-term adaptation at the edge while preserving data privacy. However, the high computational and memory demands of backpropagation pose significant challenges for ultra-low-power, memory-constrained extreme-edge devices. These challenges are further amplified for attention-based models due to their architectural complexity and computational scale. We present TrainDeeploy, a framework that unifies efficient inference and on-device training on heterogeneous ultra-low-power System-on-Chips (SoCs). TrainDeeploy provides the first complete on-device training pipeline for extreme-edge SoCs supporting both Convolutional Neural Networks (CNNs) and Transformer models, together with multiple training strategies such as selective layer-wise fine-tuning and Low-Rank Adaptation (LoRA). On a RISC-V-based heterogeneous SoC, we demonstrate the first end-to-end on-device fine-tuning of a Compact Convolutional Transformer (CCT), achieving up to 11 trained images per second. We show that LoRA reduces dynamic memory usage by 23%, decreases the number of trainable parameters and gradients by 15x, and reduces memory transfer volume by 1.6x compared to full backpropagation. TrainDeeploy achieves up to 4.6 FLOP/cycle on CCT (0.28M parameters, 71-126M FLOPs) and up to 13.4 FLOP/cycle on Deep-AE (0.27M parameters, 0.8M FLOPs), while expanding the scope of prior frameworks to support both CNN and Transformer models with parameter-efficient tuning on extreme-edge platforms.

Run Wang, Victor J. B. Jung, Philip Wiese +3

Integrated Systems Laboratory (IIS), ETH Zurich, Switzerland · Department of Electrical, Electronic and Information Engineering (DEI), University of Bologna, Italy · Department of Control and Computer Engineering (DAUIN), Politecnico di Torino, Italy

On-Device Training Edge ML Memory-Efficient Fine-Tuning Parameter-Efficient Fine-Tuning

Ask PDF

Mar 10, 2026

Two Teachers Better Than One: Hardware-Physics Co-Guided Distributed Scientific Machine Learning

Scientific machine learning (SciML) is increasingly applied to in-field processing, controlling, and monitoring; however, wide-area sensing, real-time demands, and strict energy and reliability constraints make centralized SciML implementation impractical. Most SciML models assume raw data aggregation at a central node, incurring prohibitively high communication latency and energy costs; yet, distributing models developed for general-purpose ML often breaks essential physical principles, resulting in degraded performance. To address these challenges, we introduce EPIC, a hardware- and physics-co-guided distributed SciML framework, using full-waveform inversion (FWI) as a representative task. EPIC performs lightweight local encoding on end devices and physics-aware decoding at a central node. By transmitting compact latent features rather than high-volume raw data and by using cross-attention to capture inter-receiver wavefield coupling, EPIC significantly reduces communication cost while preserving physical fidelity. Evaluated on a distributed testbed with five end devices and one central node, and across 10 datasets from OpenFWI, EPIC reduces latency by 8.9

\times

and communication energy by 33.8

\times

, while even improving reconstruction fidelity on 8 out of 10 datasets.

Yuchen Yuan, Junhuan Yang, Hao Wan +4

George Mason University, Fairfax, VA, USA · University of North Carolina at Chapel Hill, NC, USA

Scientific ML Edge ML Energy-Efficient ML Physics-Informed ML Inverse Problems

Ask PDF

Feb 24, 2026

TT-SEAL: TTD-Aware Selective Encryption for Adversarially-Robust and Low-Latency Edge AI

Cloud-edge AI must jointly satisfy model compression and security under tight device budgets. While Tensor-Train Decomposition (TTD) shrinks on-device models, prior selective-encryption studies largely assume dense weights, leaving its practicality under TTD compression unclear. We present TT-SEAL, a selective-encryption framework for TT-decomposed networks. TT-SEAL ranks TT cores with a sensitivity-based importance metric, calibrates a one-time robustness threshold, and uses a value-DP optimizer to encrypt the minimum set of critical cores with AES. Under TTD-aware, transfer-based threat models (and on an FPGA-prototyped edge processor) TT-SEAL matches the robustness of full (black-box) encryption while encrypting as little as 4.89-15.92% of parameters across ResNet-18, MobileNetV2, and VGG-16, and drives the share of AES decryption in end-to-end latency to low single digits (e.g., 58% -> 2.76% on ResNet-18), enabling secure, low-latency edge AI.

Kyeongpil Min, Sangmin Jeon, Jae-Jin Lee +1

†Department of Intelligent Semiconductor Engineering, Chung-Ang University, Seoul, Korea

Privacy-Preserving ML Edge ML Efficient Neural Network Inference

Ask PDF

Feb 22, 2026

Analyzing Latency Hiding and Parallelism in an MLIR-based AI Kernel Compiler

AI kernel compilation for edge devices depends on the compiler's ability to exploit parallelism and hide memory latency in the presence of hierarchical memory and explicit data movement. This paper reports a benchmark methodology and corresponding results for three compiler-controlled mechanisms in an MLIR-based compilation pipeline: vectorization (Vec), multi-threading (MT) across hardware contexts, and double buffering (DB) using ping--pong scratchpad buffers to overlap DMA transfers with compute. Using Triton/Inductor-generated kernels, we present an ablation ladder that separates the contribution of Vec, MT, and DB, and we quantify how MT speedup scales with problem size using GELU as a representative activation kernel. The results show that vectorization provides the primary gain for bandwidth-sensitive kernels, MT delivers substantial improvements once scheduling overhead is amortized, and DB provides additional benefit when transfers and compute can be overlapped (i.e., outside the extremes of purely memory-bound or purely compute-bound behavior).

Javed Absar, Samarth Narang, Muthu Baskaran

Qualcomm Technologies International, Ltd. · Qualcomm Technologies, Inc.

High-Performance Computing Edge ML

Ask PDF

Feb 18, 2026

The Weight of a Bit: EMFI Sensitivity Analysis of Embedded Deep Learning Models

Fault injection attacks on embedded neural network models have been shown as a potent threat. Numerous works studied resilience of models from various points of view. As of now, there is no comprehensive study that would evaluate the influence of number representations used for model parameters against electromagnetic fault injection (EMFI) attacks. In this paper, we investigate how four different number representations influence the success of an EMFI attack on embedded neural network models. We chose two common floating-point representations (32-bit, and 16-bit), and two integer representations (8-bit, and 4-bit). We deployed four common image classifiers, ResNet-18, ResNet-34, ResNet-50, and VGG-11, on an embedded memory chip, and utilized a low-cost EMFI platform to trigger faults. Beyond accuracy evaluation, we characterize the injected fault pattern by analyzing the bit error rate, the spatial distribution of corrupted bytes, and the prevalence of 0xFE/0xFF byte values across formats, identifying the mechanisms responsible for the observed differences in resilience. Our results show that while floating-point representations exhibit almost a complete degradation in accuracy (Top-1 and Top-5) after a single fault injection, integer representations offer better resistance overall. In particular, the 8-bit representation on a relatively large network (VGG-11) retains Top-1 accuracy of around 70% and Top-5 at around 90%.

Jakub Breier, Štefan Kučerák, Xiaolu Hou

TTControl GmbH, Vienna, Austria. · the Faculty of Informatics and Information Technologies, Slovak University of Technology, Slovakia. · the State Key Laboratory of Blockchain and Data Security , Zhejiang University.

Neural Network Robustness Edge ML

Ask PDF

Feb 18, 2026

U-FedTomAtt: Ultra-lightweight Federated Learning with Attention for Tomato Disease Recognition

Federated learning has emerged as a privacy-preserving and efficient approach for deploying intelligent agricultural solutions. Accurate edge-based diagnosis across geographically dispersed farms is crucial for recognising tomato diseases in sustainable farming. Traditional centralised training aggregates raw data on a central server, leading to communication overhead, privacy risks and latency. Meanwhile, edge devices require lightweight networks to operate effectively within limited resources. In this paper, we propose U-FedTomAtt, an ultra-lightweight federated learning framework with attention for tomato disease recognition in resource-constrained and distributed environments. The model comprises only 245.34K parameters and 71.41 MFLOPS. First, we propose an ultra-lightweight neural network with dilated bottleneck (DBNeck) modules and a linear transformer to minimise computational and memory overhead. To mitigate potential accuracy loss, a novel local-global residual attention (LoGRA) module is incorporated. Second, we propose the federated dual adaptive weight aggregation (FedDAWA) algorithm that enhances global model accuracy. Third, our framework is validated using three benchmark datasets for tomato diseases under simulated federated settings. Experimental results show that the proposed method achieves 0.9910% and 0.9915% Top-1 accuracy and 0.9923% and 0.9897% F1-scores on SLIF-Tomato and PlantVillage tomato datasets, respectively.

Romiyal George, Sathiyamohan Nishankar, Selvarajah Thuseethan +4

Department of Computer Engineering, University of Peradeniya, Sri Lanka. · Faculty of Science and Technology, Charles Darwin University, Australia. · Canadian Institute for Cybersecurity, University of New Brunswick, Canada. +1

Lightweight Neural Networks Federated Learning Plant Disease Classification Federated Learning Aggregation Edge ML Attention Mechanisms

Ask PDF

Feb 17, 2026

Self-Evolving Multi-Agent Network for Industrial IoT Predictive Maintenance

Industrial IoT predictive maintenance requires systems capable of real-time anomaly detection without sacrificing interpretability or demanding excessive computational resources. Traditional approaches rely on static, offline-trained models that cannot adapt to evolving operational conditions, while LLM-based monolithic systems demand prohibitive memory and latency, rendering them impractical for on-site edge deployment. We introduce SEMAS, a self-evolving hierarchical multi-agent system that distributes specialized agents across Edge, Fog, and Cloud computational tiers. Edge agents perform lightweight feature extraction and pre-filtering; Fog agents execute diversified ensemble detection with dynamic consensus voting; and Cloud agents continuously optimize system policies via Proximal Policy Optimization (PPO) while maintaining asynchronous, non-blocking inference. The framework incorporates LLM-based response generation for explainability and federated knowledge aggregation for adaptive policy distribution. This architecture enables resource-aware specialization without sacrificing real-time performance or model interpretability. Empirical evaluation on two industrial benchmarks (Boiler Emulator and Wind Turbine) demonstrates that SEMAS achieves superior anomaly detection performance with exceptional stability under adaptation, sustains prediction accuracy across evolving operational contexts, and delivers substantial latency improvements enabling genuine real-time deployment. Ablation studies confirm that PPO-driven policy evolution, consensus voting, and federated aggregation each contribute materially to system effectiveness. These findings indicate that resource-aware, self-evolving 1multi-agent coordination is essential for production-ready industrial IoT predictive maintenance under strict latency and explainability constraints.

Rebin Saleh, Khanh Pham Dinh, Balázs Villányi +1

Department of Electronics Technology, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, Műegyetem rkp. 3, H-1111 Budapest, Hungary · DataScienceWorld.Kan, Hanoi, Vietnam · Department of Computer Science, The University of Alabama at Birmingham, 1720 University Blvd, Birmingham, AL 35294 USA

Predictive Maintenance Industrial Anomaly Detection Online Anomaly Detection Multi-Agent Systems Interpretable Anomaly Detection Edge ML

Ask PDF

Feb 16, 2026

Triplet Feature Fusion for Equipment Anomaly Prediction : An Open-Source Methodology Using Small Foundation Models

Predicting equipment anomalies before they escalate into failures is a critical challenge in industrial facility management. Existing approaches rely either on hand-crafted threshold rules, which lack generalizability, or on large neural models that are impractical for on-site, air-gapped deployments. We present an industrial methodology that resolves this tension by combining open-source small foundation models into a unified 1,116-dimensional Triplet Feature Fusion pipeline. This pipeline integrates: (1) statistical features (x in

R^{28}

) derived from 90-day sensor histories, (2) time-series embeddings (y in

R^{64}

) from a LoRA-adapted IBM Granite TinyTimeMixer (TTM, 133K parameters), and (3) multilingual text embeddings (z in

R^{1024}

) extracted from Japanese equipment master records via multilingual-e5-large. The concatenated triplet h = [x; y; z] is processed by a LightGBM classifier (< 3 MB) trained to predict anomalies at 30-, 60-, and 90-day horizons. All components use permissive open-source licenses (Apache 2.0 / MIT). The inference-time pipeline runs entirely on CPU in under 2 ms, enabling edge deployment on co-located hardware without cloud dependency. On a dataset of 64 HVAC units comprising 67,045 samples, the triplet model achieves Precision = 0.992, F1 = 0.958, and ROC-AUC = 0.998 at the 30-day horizon. Crucially, it reduces the False Positive Rate from 0.6 percent (baseline) to 0.1 percent - an 83 percent reduction attributable to equipment-type conditioning via text embedding z. Cluster analysis reveals that the embeddings align time-series signatures with distinct fault archetypes, explaining how compact multilingual representations improve discrimination without explicit categorical encoding.

Takato Yasuno

Anomaly Detection Predictive Maintenance Feature Fusion Edge ML

Ask PDF

Nov 27, 2025

AutoTailor: Automatic and Efficient Adaptive Model Deployment for Diverse Edge Devices

On-device machine learning (ML) has become a fundamental component of emerging mobile applications. Adaptive model deployment delivers efficient inference for heterogeneous device capabilities and performance requirements through customizing neural architectures. SuperNet-based approaches offer a promising solution by generating numerous model variants from a pre-trained ML model. However, applying SuperNet in existing frameworks requires tedious model-aware development and time-consuming hardware-aware profiling, which limits their practical adoption. We present AutoTailor, the first framework to enable automated, end-to-end SuperNet-based adaptive model deployment for edge devices. Unlike manual SuperNet construction, AutoTailor employs a computation graph-guided compilation approach to automatically transform user-provided ML models into SuperNets. To support efficient specialization, AutoTailor incorporates learning-free latency and accuracy predictors, enabling low-cost yet accurate performance prediction. Our extensive evaluations demonstrate that AutoTailor reduces the lines of code for SuperNet construction by 10.8--34.5

\times

, reduces predictor profiling time by 2.2--11.5

\times

, and achieves up to 15.60% absolute accuracy improvement and 60.03% latency reduction compared to state-of-the-art approaches across diverse models and devices. AutoTailor's source code is publicly available at https://github.com/liu-mengyang/AutoTailor.

Mengyang Liu, Chenyu Lu, Haodong Tian +7

Southeast University · Hong Kong University of Science and Technology · Tsinghua University +1

Edge ML Efficient Neural Network Inference On-Device Inference Hardware-Aware NAS

Ask PDF

Sep 29, 2025

BiHDTrans: binary hyperdimensional transformer for efficient multivariate time series classification

The proliferation of Internet-of-Things (IoT) devices has led to an unprecedented volume of multivariate time series (MTS) data, requiring efficient and accurate processing for timely decision-making in resource-constrained edge environments. Hyperdimensional (HD) computing, with its inherent efficiency and parallelizability, has shown promise in classification tasks but struggles to capture complex temporal patterns, while Transformers excel at sequence modeling but incur high computational and memory overhead. We introduce BiHDTrans, an efficient neurosymbolic binary hyperdimensional Transformer that integrates self-attention into the HD computing paradigm, unifying the representational efficiency of HD computing with the temporal modeling power of Transformers. Empirically, BiHDTrans outperforms state-of-the-art (SOTA) HD computing models by at least 14.47% and achieves 6.67% higher accuracy on average than SOTA binary Transformers. With hardware acceleration on FPGA, our pipelined implementation leverages the independent and identically distributed properties of high-dimensional representations, delivering 39.4 times lower inference latency than SOTA binary Transformers. Theoretical analysis shows that binarizing in holographic high-dimensional space incurs significantly less information distortion than directly binarizing neural networks, explaining BiHDTrans's superior accuracy. Furthermore, dimensionality experiments confirm that BiHDTrans remains competitive even with a 64% reduction in hyperspace dimensionality, surpassing SOTA binary Transformers by 1-2% in accuracy with 4.4 times less model size, as well as further reducing the latency by 49.8% compare to the full-dimensional baseline. Together, these contributions bridge the gap between the expressiveness of Transformers and the efficiency of HD computing, enabling accurate, scalable, and low-latency MTS classification.

Jingtao Zhang, Yi Liu, Qi Shen +1

School of Biomedical Engineering, Shenzhen Campus of Sun Yat-sen University · College of Medicine and Biological Information Engineering, Northeastern University

Efficient Neural Network Inference Transformer Time Series Classification Hyperdimensional Computing Edge ML

Ask PDF